检索结果-内蒙古大学图书馆

Hybrid Learning Network: A Novel Architecture for Fast Learning

Procedia Computer Science 2017年 122卷 622-628页

作者： Ying Liu Chao Xiang School of Computer and Engineering University of Chinese Academy of Sciences Beijing 100190 China Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China

There’re many effective architectures of the artificial neural network(ANN). For which the training is a hard work. The cost for training an ANN increases exponentially when the ANN gets deeper or wider. We therefore propose a novel architecture, the Hybrid Learning Network(HLN), to achieve a fast learning with good stablity. The HLN can learn from both lab.led data and unlab.led data at the same time in a hybrid learning manner. It uses a Self Organizing Map unified by the specially designed nonlinear function as the sparsity mask for a hidden layer to improve the training speed. We experiment our architecture on a synthetic dataset to test its regression capability against the traditional architecture, the result is promising.

关键词： hybrid learning neural network sparsity mask self organizing map fast learning

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2017年

作者： Dong, Jianfeng Li, Xirong Xu, Duanqing College of Computer Science and Technology Zhejiang University Hangzhou310027 China Key Lab of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing100872 China

—In order to retrieve unlab.led images by textual queries, cross-media similarity computation is a key ingredient. Although novel methods are continuously introduced, little has been done to evaluate these methods together with large-scale query log analysis. Consequently, how far have these methods brought us in answering real-user queries is unclear. Given baseline methods that use relatively simple text/image matching, how much progress have advanced models made is also unclear. This paper takes a pragmatic approach to answering the two questions. Queries are automatically categorized according to the proposed query visualness measure, and later connected to the evaluation of multiple cross-media similarity models on three test sets. Such a connection reveals that the success of the state-of-the-art is mainly attributed to their good performance on visual-oriented queries, which account for only a small part of real-user queries. To quantify the current progress, we propose a simple text2image method, representing a novel query by a set of images selected from large-scale query log. Consequently, computing cross-media similarity between the query and a given image boils down to comparing the visual similarity between the given image and the selected images. Image retrieval experiments on the challenging Clickture dataset show that the proposed text2image is a strong baseline, comparing favorably to recent deep learning alternatives. Copyright © 2017, The Authors. All rights reserved.

关键词： Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Creating knowledge and Wisdom via Big data Analytics: Preface for ITQM 2017

引用

Procedia Computer Science 2017年 122卷 1-9页

作者： Ahuja, Vandana Shi, Yong Khazanchi, Deepak Abidi, Naseem Tian, Yingjie Berg, Daniel Tien, James M. Jaypee Business School A-10 Sector-62 Noida Uttar Pradesh201 307 India School of Economics and Management University of Chinese Academy of Sciences Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China College of Information Science and Technology University of Nebraska at Omaha Chinese Academy of Sciences OmahaNE68182 United States College of Engineering University of Miami Coral GablesFL33124 United States

来源：评论

学校读者我要写书评

暂无评论

Predicting visual features from text for image and video caption retrieval

arXiv

引用

arXiv 2017年

作者： Dong, Jianfeng Li, Xirong Snoek, Cees G.M. College of Computer Science and Technology Zhejiang University Hangzhou310027 China Key Lab of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing100872 China Informatics Institute University of Amsterdam Amsterdam1098 XH Netherlands

This paper strives to find amidst a set of sentences the one best describing the content of a given image or video. Different from existing works, which rely on a joint subspace for their image and video caption retrieval, we propose to do so in a visual space exclusively. Apart from this conceptual novelty, we contribute Word2VisualVec, a deep neural network architecture that learns to predict a visual feature representation from textual input. Example captions are encoded into a textual embedding based on multi-scale sentence vectorization and further transferred into a deep visual feature of choice via a simple multi-layer perceptron. We further generalize Word2VisualVec for video caption retrieval, by predicting from text both 3-D convolutional neural network features as well as a visual-audio representation. Experiments on Flickr8k, Flickr30k, the Microsoft Video Description dataset and the very recent NIST TrecVid challenge for video caption retrieval detail Word2VisualVec's properties, its benefit over textual embeddings, the potential for multimodal query composition and its state-of-the-art results. Copyright © 2017, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A collab.rative join scheme on a MIC-based heterogeneous platform

A collaborative join scheme on a MIC-based heterogeneous pla...

引用

Lecture Notes in Computer Science

作者： Zhou, Kailai Sun, Hui Chen, Hong Wu, Tianzhen Li, Cuiping Key Lab of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing China School of Computer and Information Southwest Forestry University Kunming China

ISBN: (纸本)9783319458168

Join is one of the most important operations in data analytics systems. Prior works focus mainly on join optimization using GPUs, but little is known about performance impact on the MICs. In order to investigate potential benefits of the use of MIC accelerators in improving performance of join operation, in this paper we design a join scheme with a CPU and MICs working collab.ratively. This scheme includes task partitioning, a data transfer mode, join algorithm design. Experimental results show that our collective join scheme is effective for a heterogeneous platform with two Xeon Phi cards, and can improve performance by up to 30 % over the CPU-only platform. © Springer International Publishing Switzerland 2016.

关键词： data transfer

来源：评论

学校读者我要写书评

暂无评论

Metric based on multi-order spaces for cross-modal retrieval

Metric based on multi-order spaces for cross-modal retrieval

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Liang Zhang Bingpeng Ma Guorong Li Qingming Huang Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Computer and Control Engineering University of Chinese Academy of Sciences China Key Lab of Intell. Info. Process. Inst. of Comput. Tech. CAS China

ISBN: (纸本)9781509060689

This paper proposes a novel method for cross-modal retrieval. Different from vector (text)-to-vector (image) framework of the traditional cross-modal methods, we adopt a vector (text)-to-matrix (image) framework. We assume that compared with vectors, matrices can directly represent images and characterize the structure of feature space. Furthermore, we propose a Metric based on Multi-order spaces (MMs). Multi-order statistic features are used to represent images for enriching the semantic information, and metrics among the multi-spaces are jointly learned to measure the similarity between two different modalities. Specifically, there are three steps for MMs. First, we jointly use the bags of visual features (zero-order), mean (first-order) and covariance (second-order) to characterize each image. Second, considering that covariance matrices and vectors lie on a Riemannian manifold and an Euclidean space respectively, we embed multi-order spaces into their corresponding Hilbert spaces to reduce the heterogeneity among the original spaces. Finally, the similarity between two different modalities can be measured by learning multiple transformations from the different Hilbert spaces to a common subspace. The performance of the proposed method over the state-of-the-art has been demonstrated through the experiments on two public datasets.

关键词： Hilbert space Manifolds Correlation Covariance matrices Feature extraction Linear programming

来源：评论

学校读者我要写书评

暂无评论

Biogeography-based optimization for cluster analysis

Biogeography-based optimization for cluster analysis

引用

International Conference on Computer, Communication and Computational Sciences, ICCCCS 2016

作者： Wu, Xueyan Wang, Hainan Chen, Zhimin Lu, Zhihai Phillips, Preetha Wang, Shuihua Zhang, Yudong School of Computer Science and Technology Nanjing Normal University NanjingJiangsu210023 China Key Laboratory of Statistical Information Technology & Data Mining State Statistics Bureau ChengduSichuan610225 China School of Computer and Information Engineering Henan Normal University XinxiangHenan453000 China School of Electronic Information Shanghai Dianji University Shanghai200240 China Key Laboratory of Symbolic Computation & Knowledge Engineering of Ministry of Education Jilin University ChangchunJilin130012 China Guangxi Key Laboratory of Manufacturing System & Advanced Manufacturing Technology GuilinGuangxi541004 China School of Natural Sciences and Mathematics Shepherd University ShepherdstownWV25443 United States West Virginia School of Osteopathic Medicine 400 N Lee St LewisburgWV24901 United States Department of Electrical Engineering The City College of New York CUNY New YorkNY10031 United States State Key Lab of CAD & CG Zhejiang University HangzhouZhejiang310027 China Manchester Metropolitan University ManchesterM156BH United Kingdom

ISBN: (纸本)9789811037696

With the aim of resolving the issue of cluster analysis more precisely and validly, a new approach was proposed based on biogeography-based optimization (abbreviated as BBO) algorithm. (Method) First, we reformulated the problem with an optimization model based on the variance ratio criterion (VARAC). Then, BBO was presented to search the optimal solution of the VARAC. There are 400 data of four groups in the experimental dataset, which have the degrees of overlapping of three distinct scales. The first one is nonoverlapping, the second one is partial overlapping, and the last is severely overlapping. BBO algorithm was compared with three different state-of-the-art approaches. We ran every algorithm 20 times. In this experiment, our results demonstrate the maximum VARAC values that can be found by BBO. The conclusion is that BBO is predominant which is extremely quick for the issue of clustering analysis. © Springer Nature Singapore Pte Ltd. 2017.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring outliers in crowdsourced ranking for QoE

arXiv

引用

arXiv 2017年

作者： Xu, Qianqian Yan, Ming Huang, Chendi Xiong, Jiechao Huang, Qingming Yao, Yuan Institute of Information Engineering Cas Beijing100093 Department of Computational Mathematics Michigan State University East LansingMI48824 United States BICMR-LMAM-LMEQF-LMP School of Mathematical Sciences Peking University Beijing100871 Tencent Ai Lab Shenzhen518057 University of Chinese Academy of Sciences Beijing100049 China Key Lab of Intell. Info. Process. Inst. of Comput. Tech. Cas Beijing100190 Key Lab of Big Data Mining and Knowledge Management Cas Beijing100190 Department of Mathematics Hong Kong University of Science and Technology 100871 Hong Kong

Outlier detection is a crucial part of robust evaluation for crowd-sourceable assessment of Quality of Experience (QoE) and has attracted much attention in recent years. In this paper, we propose some simple and fast algorithms for outlier detection and robust QoE evaluation based on the nonconvex optimization principle. Several iterative procedures are designed with or without knowing the number of outliers in samples. Theoretical analysis is given to show that such procedures can reach statistically good estimates under mild conditions. Finally, experimental results with simulated and real-world crowdsourcing datasets show that the proposed algorithms could produce similar performance to Huber-LASSO approach in robust ranking, yet with nearly 8 or 90 times speed-up, without or with a prior knowledge on the sparsity size of outliers, respectively. Therefore the proposed methodology provides us a set of helpful tools for robust QoE evaluation with crowdsourcing data. Copyright © 2017, The Authors. All rights reserved.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Rucmm at MediaEval 2015 Affective impact of movies task: Fusion of audio and visual cues

Rucmm at MediaEval 2015 Affective impact of movies task: Fus...

引用

Multimedia Benchmark Workshop, MediaEval 2015

作者： Jin, Qin Li, Xirong Cao, Haibing Huo, Yujia Liao, Shuai Yang, Gang Xu, Jieping Multimedia Computing Lab School of Information Renmin University of China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

This paper summarizes our efforts for the first time participation in the Violent Scene Detection subtask of the MediaEval 2015 Affective Impact of Movies Task. We build violent scene detectors using both audio and visual cues. In particular, the audio cue is represented by bag-of-audio-words with fisher vector encoding. The visual cue is exploited by extracting CNN features from video frames. The detectors are implemented using two-class linear SVM classifiers. Evaluation shows that the audio detectors and the visual detectors are comparable and complementary to each other. Among our submissions, multi-modal late fusion leads to the best performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards structured semantic embedding of multimedia 15

Towards structured semantic embedding of multimedia

引用

7th International Conference on Internet Multimedia Computing and Service, ICIMCS 2015

作者： Li, Xirong Huo, Yujia Lan, Weiyu He, Xixi Liao, Shuai Key Lab of Data Engineering and Knowledge Engineering Renmin University of China 100872 China Multimedia Computing Lab School of Information Renmin University of China 100872 China

ISBN: (纸本)9781450335287

This abstract paper sketches our research towards Struc-tured Semantic Embedding of multimedia data. Though a tag may have multiple senses with completely different visual imagery, current semantic embedding methods represent the tag by a single vector regardless of its senses. We challenge this convention, arguing the importance of adding seman-tic structures into semantic embedding. In particular, we develop Hierarchical Semantic Embedding, a simple model that exploits the WordNet hierarchy to make the semantic embedding structured to some extent. We demonstrate the viability of structured semantic embedding for tag disam-biguation and zero-shot image tagging. © 2015 ACM.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：